package main

import (
	"fmt"
	"sync"
)

type SafeMap struct{
	v   map[string]bool
	sync.Mutex
}

var safemap = SafeMap{
	v:make(map[string]bool),
}

type Fetcher interface {
	// Fetch 返回 URL 的 body 内容，并且将在这个页面上找到的 URL 放到一个 slice 中。
	Fetch(url string) (body string, urls []string, err error)
}

// Crawl 使用 fetcher 从某个 URL 开始递归的爬取页面，直到达到最大深度。
// sync.WaitGroup 是结构体，必须传指针,否则会死锁
func Crawl(url string, depth int, fetcher Fetcher, waitgroup *sync.WaitGroup) {
	defer waitgroup.Done()
	if depth <= 0 {
		return
	}
	safemap.Lock()
	if isfetch := safemap.v[url]; isfetch {
		fmt.Println(url," is fetched")
		// 此处容易忘记解锁
		safemap.Unlock()
		return
	} else {
		safemap.v[url] = true
		safemap.Unlock()
	}
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		return
	}
	fmt.Printf("found: %s %q\n", url, body)
	wg := sync.WaitGroup{}
	for _, u := range urls {
		wg.Add(1)
		go Crawl(u, depth-1, fetcher, &wg)
	}
	wg.Wait()
	return
}

func main() {
	wg := sync.WaitGroup{}
	wg.Add(1)
	go Crawl("http://golang.org/", 4, fetcher, &wg)
	wg.Wait()
}

// fakeFetcher 是返回若干结果的 Fetcher。
type fakeFetcher map[string]*fakeResult

type fakeResult struct {
	body string
	urls []string
}

func (f fakeFetcher) Fetch(url string) (string, []string, error) {
	if res, ok := f[url]; ok {
		return res.body, res.urls, nil
	}
	return "", nil, fmt.Errorf("not found: %s", url)
}

// fetcher 是填充后的 fakeFetcher。
var fetcher = fakeFetcher{
	"http://golang.org/": &fakeResult{
		"The Go Programming Language",
		[]string{
			"http://golang.org/pkg/",
			"http://golang.org/cmd/",
		},
	},
	"http://golang.org/pkg/": &fakeResult{
		"Packages",
		[]string{
			"http://golang.org/",
			"http://golang.org/cmd/",
			"http://golang.org/pkg/fmt/",
			"http://golang.org/pkg/os/",
		},
	},
	"http://golang.org/pkg/fmt/": &fakeResult{
		"Package fmt",
		[]string{
			"http://golang.org/",
			"http://golang.org/pkg/",
		},
	},
	"http://golang.org/pkg/os/": &fakeResult{
		"Package os",
		[]string{
			"http://golang.org/",
			"http://golang.org/pkg/",
		},
	},
}